Harryfloyd Substack
A Google Mistake Taught an AI to Hide Its Shortcuts. Eight States Say OpenAI Hid ChatGPT's Risks.
3 mins
NewsDeep Reads.
Top-tier AI blogs, technical tutorials, and research analysis written by the people shaping the industry.
Last Brew Time: Oct 17, 2026, 11:34 AM PT
Featured Articles
Towards AI (Medium)
Train Once, Reuse Later: Three Tests of Skipping BCI Calibration
10 mins
Research
ByteByteGo
EP229: 8 Chunking strategies for RAG-based agents
6 mins
Tutorial
Thezvi Substack
Leaked Anthropic Draft AI Regulatory Bill Is Unacceptable and Troubling
5 mins
Analysis
Interconnects
Meta shakes up the frontiers, open and closed
5 mins
AnalysisTowards AI (Medium)
Are AI Agents Going Rogue? What’s Actually Happening?
9 mins
AnalysisTowards AI (Medium)
LLM Harness Engineering: The Missing Architecture Behind Reliable AI Agents
9 mins
Analysis
Msukhareva Substack
What You Can Do With Open-Weight AI That OpenAI and Anthropic Won’t Let You
5 mins
Analysis
Aiengineeringinsider Substack
Beyond Basic RAG: 12 Production Architectures Every AI Engineer Should Know
6 mins
TutorialSimon Willison
Quoting Addy Osmani, Morgan Westlee Lunt, and Qing Wang
6 mins
Analysis
Aiscientist Substack
MiniCorp: The Last Mile to an AI Agent Corporation
7 mins
Research
Amazon Engineering
Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCore
5 mins
Analysis
Oreillyradar Substack
This Week in AI: Expanding the Possibilities
3 mins
News